© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124791
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imetype
    0.42
     kah
    0.38
     IAM
    0.36
    ifica
    0.36
    éraire
    0.36
    ogluc
    0.36
    Collapsed
    0.35
    咦
    0.35
     pendent
    0.34
    rate
    0.34
    POSITIVE LOGITS
     Bun
    0.42
    のア
    0.42
     Ni
    0.40
     홍
    0.39
    啇
    0.39
    搾
    0.39
     ヤ
    0.38
     Gris
    0.37
     സ
    0.37
     Бу
    0.37
    Activations Density 0.000%

    No Known Activations